This HyperNEAT package contains source code and executables for the HyperNEAT method for evolving large-scale neural networks with regularities and symmetries that exploit task geometry.  This package specifically includes the simple visual discrimination experiment described in this paper, in which working neural networks with millions of connections were produced.  The package also comes with several sample networks (generated by connective Compositional Pattern Producing Networks, i.e. connective CPPNs) included from that experiment  We encourage you to build new experiments with HyperNEAT.

Version 2.0 (April 2008) contains the checkers experiments mentioned in this paper .

Version 2.2 (July 2008) includes a way to disable the GUI interface when building.

Version 2.3 (August 2008) Has a fix to be backwards compatible with the experiments from version 1.0

Version 2.5 (September 2008) includes more bug fixes and performance enhancements.

Download Version 2.5 here: Windows & Linux

For questions, comments, or suggestions, please email This e-mail address is being protected from spam bots, you need JavaScript enabled to view it This e-mail address is being protected from spam bots, you need JavaScript enabled to view it .    

Here are links to the Version 1.0 source code:

The source code has been moved to the UCF eplex site:

HyperNEAT Source Code V 1.0 (Windows)

HyperNEAT Source Code V. 1.0 (Linux)

View the README for more details